A method for allocating group intelligence perception tasks and related equipment

Abstract

The present invention provides a method for allocating tasks for crowd-sensing and related equipment, comprising: obtaining historical trajectory data of multiple target participants in a crowd-sensing platform, determining the movement pattern of each target participant, and calculating the self-coverage and uncertainty of each target participant; performing vehicle trajectory comparison for any two target participants respectively, and calculating the uncertainty of the coverage between the two target participants; combining the multiple target participants according to their own coverage, uncertainty, and the uncertainty of the coverage between the target participants to obtain a combination result, calculating the overall coverage, uncertainty, and range of the uncertainty of the combination result, and setting a control factor based on the range of the uncertainty; obtaining a combination weight matrix according to the control factor and determining an optimal combination scheme of the target participants; obtaining a task allocation result according to the optimal combination scheme; and improving the task coverage while reducing the impact of uncertainty on the task coverage.

Description

Technical Field

[0001] The present invention relates to the technical field of crowd sensing data acquisition, and in particular to a crowd sensing task allocation method and related equipment. Background Art

[0002] Crowd perception is a new data acquisition model that combines crowdsourcing ideas and the perception capabilities of mobile devices. It can dynamically collect perception data at a very low cost by using only the user's smart devices.

[0003] A key issue in crowdsensing is recruiting enough participants to achieve high task coverage. Crowdsensing tasks are location-based. High task coverage means participants equipped with sensing devices can collect data from a wide area. The effectiveness of crowdsensing services is determined by the coverage of the task. For example, in a navigation system, accurate route recommendations to avoid congestion can only be made if city-wide traffic congestion information is available. Low traffic information coverage can affect the effectiveness of route recommendations. Therefore, it is necessary to design an effective task allocation method to select appropriate participants to improve the coverage of crowdsensing tasks. While improving crowdsensing coverage, it is also important to consider the timeliness of the task. This is because the timeliness of crowdsensing tasks means that outdated data becomes worthless. However, in reality, the movement of participants is uncertain. Participants cannot guarantee that they will arrive at the designated task area within the specified time to complete the task. This makes the ultimate coverage of the crowdsensing task uncertain, and thus the effectiveness of the task cannot be guaranteed. Therefore, if a reasonable task allocation mechanism can be designed and appropriate participants can be selected to improve coverage while reducing uncertainty, the effectiveness and stability of crowd sensing services can be guaranteed.

[0004] Existing task allocation methods for improving crowdsensing coverage have several issues. Most fail to consider the impact of uncertainty. When participant trajectories are uncertain, neither the platform nor the participants themselves can guarantee that they will complete the task within the specified timeframe. Even if these methods optimize the selection of low-cost, high-quality participants for the task, the presence of uncertainty can cause these methods to significantly deviate from expected results in real-world environments. For example, participants may not be able to cover enough of the task area due to traffic congestion; or two target participants may have the same trajectories, resulting in duplicate data collection and waste. The presence of uncertainty can render these optimal task allocation strategies, which don't account for uncertainty, ineffective and suboptimal. In addition to the aforementioned research, some task allocation methods consider the impact of uncertainty, but only address it without eliminating it. These methods mitigate the impact of uncertainty by recruiting more participants. This practice of reducing uncertainty by increasing redundancy through recruiting additional participants can reduce the overall coverage of the crowdsensing task, thereby reducing its effectiveness. Other task allocation methods attempt to eliminate uncertainty by predicting user trajectories. However, it is difficult to accurately predict future trajectories based solely on a participant's historical trajectory. Taking taxi drivers as an example, these methods can only learn from their own movement patterns. However, the taxi's future trajectory is affected by a variety of factors, including customer demand, road conditions, and traffic control. Taxi drivers will flexibly adjust their routes, making their final trajectory difficult to predict. Furthermore, since the accuracy of predicting the movement trajectory of a single target participant is low, predicting the movement of multiple target participants and determining whether their future trajectories will overlap is even more difficult, which wastes resources. Because the effectiveness of these methods in reducing uncertainty depends on the accuracy of trajectory prediction, they cannot effectively eliminate uncertainty when the accuracy is low. Summary of the Invention

[0005] The present invention provides a crowd-sensing task allocation method and related equipment, the purpose of which is to improve task coverage while reducing the impact of uncertainty on task coverage.

[0006] In order to achieve the above object, the present invention provides a method for allocating group intelligence perception tasks, comprising:

[0007] Step 1: Obtain historical trajectory data of multiple target participants in the crowd sensing platform and determine the mobility pattern of each target participant based on the historical trajectory data. The mobility pattern includes vehicle speed and regional distribution of vehicle trajectory.

[0008] Step 2: Calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the mobility pattern of each target participant. The self-coverage rate represents the amount of the task area covered by the target participant's vehicle trajectory, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate.

[0009] Step 3: For each target participant, compare the vehicle trajectories of any two target participants to obtain the correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation;

[0010] Step 4: Combine multiple target participants based on their own coverage, the uncertainty of their own coverage, and the uncertainty of coverage among target participants to obtain a combined result, and calculate the overall coverage of the combined result and the uncertainty of the overall coverage;

[0011] Step 5: Calculate the range of the uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and set a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of the uncertainty of the overall coverage rate;

[0012] Step 6: Solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factors to obtain a combination weight matrix, and determine the combination plan of the target participants based on the combination weight matrix;

[0013] Step 7: Assign tasks according to the target participants' combination plan to obtain the task assignment result.

[0014] Specifically, in step 2, the self-coverage of each target participant is:

[0015]

[0016] in, represents the mean coverage rate generated by the i-th target participant completing the t-th round of tasks, represents the set of areas that the vehicle trajectory of the i-th target participant passes through when completing the t-th round of tasks, Represents a region set The number of target regions in l m Represents a region set The mth target area in v m represents the coverage of the mth target area;

[0017] According to the standard deviation of each target participant's own coverage, the uncertainty of each target participant's own coverage is:

[0018]

[0019] in, represents the uncertainty of the self-coverage of the i-th target participant, N i represents the cumulative number of tasks completed by the i-th target participant, V i represents the mean coverage resulting from the target participant completing all tasks.

[0020] Specifically, in step 3, the uncertainty of the coverage between the two target participants is calculated using the global sequence alignment algorithm as:

[0021]

[0022] in, represents the uncertainty of the coverage between the i1th target participant and the i2th target participant, represents the optimal comparison path optimized by the i1th target participant, represents the optimal comparison path optimized by the i2th target participant, Represents the optimal alignment path length, express and The number of identical nodes in .

[0023] Furthermore, in step 4, multiple target participants are combined to obtain a combined result, and the coverage rate of each target participant in the combined result is weighted to obtain the overall coverage rate V p for:

[0024]

[0025] Where I represents the number of participants in the combined target; w i represents the weight of the i-th target participant in the combination;

[0026] According to the correlation of coverage between two target participants, the uncertainty of the overall coverage is obtained by performing a weighted combination and addition of the coverage of each target participant:

[0027]

[0028] in, represents the uncertainty of the overall coverage.

[0029] Furthermore, in step 5, the regulatory factor The expression is:

[0030]

[0031]

[0032]

[0033] Among them, λ is the trade-off between uncertainty and coverage set by the crowd sensing platform, ranging from (0,1). The larger λ is, the more the crowd sensing platform tends to increase the uncertainty of the overall coverage of the task; represents the maximum value of the uncertainty of the overall coverage after combining the target participants; represents the minimum uncertainty of the overall coverage after combining the target participants; f(·) represents the V p About φ p The functional relationship of a=V T A -1 V,b=V T A -1 1 I , V represents the matrix composed of the mean coverage of all target participants completing the task, A represents the covariance matrix of coverage between target participants, 1 I represents a 1×I matrix with all 1s, V T represents the matrix transpose of V, A -1 represents the inverse of matrix A, Represents matrix 1 I Transpose, λ i is the eigenvalue of the covariance matrix of the uncertainty of the i-th target participant, represents the minimum uncertainty of the coverage of all target participants themselves, It represents the maximum value of the uncertainty of the coverage of all target participants themselves.

[0034] Furthermore, in step 6, according to the regulatory factor Solve the overall coverage and the uncertainty of the overall coverage to obtain the combined weight matrix For:

[0035]

[0036] Among them, A -1 Indicates the inverse of matrix A, V p represents the overall coverage, represents the uncertainty of the overall coverage, and V represents the matrix composed of the mean coverage of all target participants completing the task.

[0037] Furthermore, the target participant's combination scheme is the combination weight matrix Center front The target participants with large weights are Indicates the number of target participants selected.

[0038] The present invention also provides a group intelligence perception task allocation device, comprising:

[0039] An acquisition module is used to obtain historical trajectory data of multiple target participants in the crowdsensing platform and determine the movement pattern of each target participant based on the historical trajectory data. The movement pattern includes vehicle speed and regional distribution of vehicle trajectory.

[0040] A calculation module is used to calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the movement pattern of each target participant, wherein the self-coverage rate represents the amount of task area covered by the vehicle trajectory of the target participant, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate;

[0041] The comparison module is used to compare the vehicle trajectories of any two target participants for each target participant, obtain the correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation;

[0042] A combination module is used to combine multiple target participants according to their own coverage, the uncertainty of their own coverage, and the uncertainty of the coverage between target participants to obtain a combination result, and calculate the overall coverage of the combination result and the uncertainty of the overall coverage;

[0043] A control factor setting module is used to calculate the range of uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and to set a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of uncertainty of the overall coverage rate;

[0044] A solution module is used to solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factors, obtain a combination weight matrix, and determine the combination plan of the target participants based on the combination weight matrix;

[0045] The task assignment module is used to assign tasks according to the combination plan of the target participants and obtain the task assignment results.

[0046] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a method for allocating group intelligence perception tasks is implemented.

[0047] The present invention also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor implements the group intelligence perception task allocation method when executing the computer program.

[0048] The above solution of the present invention has the following beneficial effects:

[0049] The present invention obtains historical trajectory data of multiple target participants in a group intelligence perception platform, and determines the movement mode of each target participant based on the historical trajectory data; calculates the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the movement mode of each target participant, wherein the self-coverage rate represents the number of task areas covered by the vehicle trajectory of the target participant, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate; for each target participant, the vehicle trajectories of any two target participants are compared to obtain the correlation between the two vehicle trajectories, and the uncertainty of the coverage rate between the two target participants is calculated based on the correlation; based on the self-coverage rate, the uncertainty of the self-coverage rate and the uncertainty of the coverage rate between the target participants, multiple target participants are combined to obtain a combination result, and the overall value of the combination result is calculated. The invention relates to a method for determining the coverage rate and the uncertainty of the overall coverage rate; calculating the range of the uncertainty of the overall coverage rate based on the overall coverage rate and the uncertainty of the overall coverage rate; setting a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of the uncertainty of the overall coverage rate; solving the overall coverage rate and the uncertainty of the overall coverage rate based on the control factor to obtain a combination weight matrix, and determining the combination scheme of the target participants based on the combination weight matrix; performing task allocation based on the combination scheme of the target participants to obtain a task allocation result; compared with the prior art, the invention quantifies the uncertainty of the participant's own coverage rate and the uncertainty between participants, measures the uncertainty of the participant's own coverage rate using fluctuation, measures the uncertainty between participants using correlation, and eliminates the uncertainty of the overall task completion by combining participants. The invention also finds the optimal participant combination through the optimization method to maximize the task coverage rate and minimize the uncertainty of task completion, and can improve the coverage rate of the crowd sensing task and reduce the uncertainty of the coverage rate under the constraint of task timeliness, so as to make the crowd sensing service more stable.

[0050] Other beneficial effects of the present invention will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of a flow chart of an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of task allocation provided by an embodiment of the present invention;

[0053] Figure 3 is a graph showing changes in coverage uncertainty in an embodiment of the present invention;

[0054] Figure 4 The figure is a comparison chart of the coverage between the embodiment of the present invention and the prior art. DETAILED DESCRIPTION

[0055] To make the technical problems, technical solutions, and advantages to be solved by the present invention more clear, the following is a detailed description with reference to the accompanying drawings and specific embodiments. It is obvious that the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0056] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0057] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to a locking connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0058] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0059] In response to existing problems, the present invention provides a method for allocating group intelligence perception tasks and related equipment.

[0060] like Figure 1 As shown, an embodiment of the present invention provides a method for allocating group intelligence sensing tasks, including:

[0061] Step 1: Obtain historical trajectory data of multiple target participants in the crowd sensing platform and determine the mobility pattern of each target participant based on the historical trajectory data. The mobility pattern includes vehicle speed and regional distribution of vehicle trajectory.

[0062] Step 2: Calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the mobility pattern of each target participant. The self-coverage rate represents the amount of the task area covered by the target participant's vehicle trajectory, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate.

[0063] Step 3: For each target participant, compare the vehicle trajectories of any two target participants to obtain the correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation;

[0064] Step 4: Combine multiple target participants based on their own coverage, the uncertainty of their own coverage, and the uncertainty of coverage among target participants to obtain a combined result, and calculate the overall coverage of the combined result and the uncertainty of the overall coverage;

[0065] Step 5: Calculate the range of the uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and set a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of the uncertainty of the overall coverage rate;

[0066] Step 6: Solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factors to obtain a combination weight matrix, and determine the combination plan of the target participants based on the combination weight matrix;

[0067] Step 7: Assign tasks according to the target participants' combination plan to obtain the task assignment result.

[0068] In the embodiment of the present invention, a group intelligence perception system environment is first established, such as Figure 2 As shown in the figure, the crowd sensing task allocation mechanism includes: task requester, crowd sensing platform and participants; participants can be taxi drivers with smart devices (such as mobile phones or tablets), and the participant set is G = {g1, g2, ..., g i ,…,g I}, where g i represents the i-th participant, and I represents the total number of participants. Assume that L={l1,l2,…,l m ,…,l M} represents the set of areas where tasks need to be completed. m The main interactions between the crowd intelligence perception platform and participants include:

[0069] (1) The crowd sensing platform publishes task information. Each time a task is released, the crowd sensing platform will publish M tasks and their task areas.

[0070] (2) Participants decide whether to participate in the task. Participants will decide whether to participate in the task based on their own circumstances and return the decision to the crowd-sensing platform;

[0071] (3) The crowd-sensing platform selects participants. After receiving the decision of the participants, the crowd-sensing platform selects appropriate target participants from the participants who are willing to participate in the task according to the crowd-sensing task allocation method provided by the present invention;

[0072] (4) The target participant completes the task and starts collecting data. After the collection is completed, the target participant sends the collected data to the crowd-sensing platform;

[0073] (5) The crowd-sensing platform confirms the data.

[0074] Specifically, the target participant's self-coverage rate is reflected in the task coverage rate of the area passed by the target participant's movement trajectory within the specified time. The target participant's activities in the area with high task coverage rate or expanding the scope of its activities per unit time will increase its coverage rate of completing tasks. Since the target participant's movement trajectory is uncertain, it is impossible to predict the target participant's self-coverage rate in the future. Therefore, the target participant's current self-coverage rate is evaluated by the mean of the historical coverage rate in the target participant's historical trajectory data. The self-coverage rate of each target participant is calculated as:

[0075]

[0076] in, represents the mean coverage rate generated by the i-th target participant completing the t-th round of tasks, represents the set of areas that the vehicle trajectory of the i-th target participant passes through when completing the t-th round of tasks, Represents a region set The number of target regions in l m Represents a region set The mth target area in v m represents the coverage of the mth target area.

[0077] Since the target participant's movement trajectory is uncertain, the coverage rate of the task is also uncertain. The intuitive manifestation is that the coverage rate of the participant's task completion in different periods fluctuates. Therefore, the uncertainty of the target participant's own coverage rate is defined as the standard deviation of the coverage rate of the task completed in the past. The uncertainty of each target participant's own coverage rate is calculated as:

[0078]

[0079] in, represents the uncertainty of the self-coverage of the i-th target participant, N i represents the cumulative number of tasks completed by the i-th target participant, V i represents the mean coverage resulting from the target participant completing all tasks.

[0080] Specifically, since the uncertainty of the target participant's own coverage rate will be affected by the correlation between participants, if the correlation between two target participants is high, the task areas passed by their trajectories are relatively similar, and selecting these two target participants at the same time will increase the uncertainty of completing the task; calculating the correlation between two target participants requires comparing the task areas passed by all target participants, and there is a situation of temporal and spatial misalignment, that is, two target participants may pass through the same area in different time periods. Therefore, the uncertainty of the coverage rate between two target participants is calculated by citing the global sequence alignment algorithm:

[0081]

[0082] in, represents the uncertainty of the coverage between the i1th target participant and the i2th target participant, represents the optimal comparison path optimized by the i1th target participant, represents the optimal comparison path optimized by the i2th target participant, Represents the optimal alignment path length, express and The number of identical nodes in .

[0083] The global sequence comparison algorithm used in the embodiment of the present invention can more accurately compare the similarity between two sequences, and can also use dynamic programming to perform complex comparisons at a faster speed to calculate the best comparison result.

[0084] Specifically, since the coverage rate of each target participant is independent, it is necessary to discuss the overall coverage rate of the combination of different target participants. The overall coverage rate can be obtained by weighting the coverage rates of each target participant. In the embodiment of the present invention, multiple target participants are combined to obtain a combined result, and the coverage rate of each target participant in the combined result is weighted to obtain the overall coverage rate V. p for:

[0085]

[0086] Where I represents the number of target participants in the combined result; w i Represents the weight of the i-th target participant in the combined result.

[0087] Specifically, since uncertainty includes not only the uncertainty of a single target participant but also the uncertainty caused by the correlation between two target participants, the overall uncertainty cannot be obtained through a simple weighted summation. Instead, it is necessary to combine and add the target participants in pairs. Therefore, according to the correlation between the coverage rates of the two target participants, the embodiment of the present invention performs weighted combination and addition on the coverage rates of the target participants in pairs, and obtains the uncertainty of the overall coverage rate as follows:

[0088]

[0089] in, represents the uncertainty of the overall coverage.

[0090] Specifically, the embodiment of the present invention defines the optimization goals of the crowd intelligence perception platform as:

[0091] (1) Under the same uncertainty, the task completion coverage is the highest;

[0092] (2) Under the same task coverage, the uncertainty of task completion coverage is the lowest.

[0093] Solving the above two-objective optimization problem will yield a series of optimal combined solutions. These solutions correspond to different task completion coverage and uncertainty. Therefore, it is necessary to determine the control factor based on the crowd-sensing platform's trade-off between uncertainty and coverage to determine the unique optimal solution that best suits the crowd-sensing platform. The optimization objective is expressed as:

[0094]

[0095] in, It represents the countless possible combinations of coverage and uncertainty due to different combination weights.

[0096] Specifically, in different situations, the different uncertainties of target participants will make the range of the control factor that the crowd intelligence perception platform can set different. Therefore, in order to facilitate the normalization setting of the factor, the embodiment of the present invention normalizes the control factor and then performs a standardized setting on the control factor. Assuming that the set value is As long as you find The mapping relationship with the control factor can determine the size of the control factor, but only by knowing the relationship between the uncertainty of the combination result and the coverage of the combination result in the optimal case can the size of the final control factor be obtained.

[0097] In order to enable the crowd intelligence perception platform to be standardized, the embodiment of the present invention normalizes the control factor, that is, the control factor The expression is:

[0098]

[0099] in, The trade-off between uncertainty and coverage set for the crowd sensing platform is in the range of (0,1). The larger it is, the more the crowdsensing platform tends to increase the uncertainty of the overall task coverage; represents the maximum value of the uncertainty of the overall coverage after combining the target participants; represents the minimum uncertainty of the overall coverage after combining the target participants; f(·) represents the V p about The functional relationship of a=V T A -1 V,b=V T A -1 1 I , V represents the matrix composed of the mean coverage of all target participants completing the task, A represents the covariance matrix of coverage between target participants, 1 I represents a 1×I matrix with all 1s, V T represents the matrix transpose of V, A -1 represents the inverse of matrix A, express and The covariance of Represents matrix 1 I Transpose.

[0100] The size of the control factor cannot be greater than the maximum coverage of all combination results. At the same time, in order to avoid the existence of suboptimal solutions, the control factor needs to be greater than the uncertainty of the minimum coverage among all combination results. Therefore, by obtaining the range of the uncertainty of the combination results, the range of the control factor can be obtained.

[0101] in, Calculated as follows:

[0102]

[0103] Among them, λ i is the eigenvalue of the covariance matrix of the uncertainty of the i-th target participant, represents the minimum value of the uncertainty of the coverage of all target participants themselves;

[0104] in, Calculated as follows:

[0105]

[0106] It represents the maximum value of the uncertainty of the coverage of all target participants themselves.

[0107] The control factor reflects the benchmark for changes in the combination coverage when uncertainty changes. The optimal combination weight matrix obtained by solving this optimization problem can be used to determine the optimal target participant combination. Solve the overall coverage and the uncertainty of the overall coverage to obtain the combined weight matrix for:

[0108]

[0109] Among them, A -1 Indicates the inverse of matrix A, V p represents the overall coverage, represents the uncertainty of the overall coverage rate, V represents the matrix composed of the mean coverage rate of all target participants completing the task; the combination scheme of the target participants is the combination weight matrix Center front The target participants with large weights are Indicates the number of target participants to be selected.

[0110] Compared to existing technologies, this embodiment of the present invention quantifies the uncertainty of a participant's own coverage and the uncertainty between participants. It uses fluctuations to measure the uncertainty within a participant, uses correlation to measure the uncertainty between participants, and eliminates the uncertainty of overall task completion by combining participants. Furthermore, an optimization method is used to find the optimal participant combination to maximize task coverage and minimize task completion uncertainty. This approach improves the coverage of crowdsensing tasks and reduces coverage uncertainty within the constraints of task timeliness, making crowdsensing services more stable.

[0111] In the embodiment of the present invention, the impact of the target participants on the uncertainty of the combination results is first evaluated, such as Figure 3The figure shows how the uncertainty of the combination results changes with the number of target participants. As can be seen, as the number of target participants in the combination increases, both the maximum and minimum uncertainty decrease. This is because the number of target participants increases, and the number of target participant combinations available increases. Furthermore, when correlation is low, fluctuations in the coverage of target participants are not synchronized. Therefore, when the coverage of one target participant in the combination decreases, the coverage of another target participant may increase, thus reducing the uncertainty of the combination result. Furthermore, it can be seen that the range of uncertainty in the combination result does not change with the number of target participants, remaining within a relatively stable range. This shows that the final target participant combination can reduce the overall uncertainty of the overall coverage.

[0112] In order to further evaluate the performance of the method provided by the embodiment of the present invention, the embodiment of the present invention is also compared with the latest DLMV mechanism, such as Figure 4 As shown. The setting of this figure is to randomly select five participants, and select three target participants from the five participants to participate in the task, and compare the size of the self-coverage of these three target participants. It can be found from the figure that the uncertainty of the method provided by the embodiment of the present invention is smaller than the uncertainty of the comparison method. At the same time, the average coverage of the method provided by the embodiment of the present invention is 13.63, which is much larger than 11.35 of the comparison method. This reflects that our invention can find the optimal solution between coverage and uncertainty, maximize the overall coverage and minimize the overall uncertainty; it can also balance uncertainty and coverage by adjusting the control factor, and make adjustments between the two.

[0113] The present invention also provides a group intelligence perception task allocation device, comprising:

[0114] An acquisition module is used to obtain historical trajectory data of multiple target participants in the crowdsensing platform and determine the movement pattern of each target participant based on the historical trajectory data. The movement pattern includes vehicle speed and regional distribution of vehicle trajectory.

[0115] A calculation module is used to calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the movement pattern of each target participant, wherein the self-coverage rate represents the amount of task area covered by the vehicle trajectory of the target participant, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate;

[0116] The comparison module is used to compare the vehicle trajectories of any two target participants for each target participant, obtain the correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation;

[0117] A combination module is used to combine multiple target participants according to their own coverage, the uncertainty of their own coverage, and the uncertainty of the coverage between target participants to obtain a combination result, and calculate the overall coverage of the combination result and the uncertainty of the overall coverage;

[0118] A control factor setting module is used to calculate the range of uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and to set a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of uncertainty of the overall coverage rate;

[0119] A solution module is used to solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factors, obtain a combination weight matrix, and determine the combination plan of the target participants based on the combination weight matrix;

[0120] The task assignment module is used to assign tasks according to the combination plan of the target participants and obtain the task assignment results.

[0121] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the embodiment of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the embodiments of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0123] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a method for allocating group intelligence perception tasks is implemented.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the embodiments of the present invention implement all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include at least: any entity or device capable of carrying the computer program code to a construction device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, a computer-readable medium cannot be an electric carrier signal or a telecommunication signal.

[0125] The present invention also provides a terminal device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor implements the group intelligence perception task allocation method when executing the computer program.

[0126] It should be noted that the terminal device may be a mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UmPC), netbook, personal digital assistant (PDA), and other terminal devices. For example, the terminal device may be a station (ST, STAiON) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SiP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, etc. The embodiments of the present invention do not impose any restrictions on the specific type of the terminal device.

[0127] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASiC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0128] In some embodiments, the memory may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. In other embodiments, the memory may also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device, a smart memory card (SmC, Smart media Card), a secure digital (SD, Secure Digital) card, a flash card, etc. Furthermore, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0129] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiments of the embodiments of the present invention. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0130] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for allocating group intelligence perception tasks, characterized in that: include: Step 1: Obtain historical trajectory data of multiple target participants in the crowd sensing platform, and determine the movement pattern of each target participant based on the historical trajectory data, wherein the movement pattern includes vehicle speed and regional distribution of vehicle trajectory; Step 2: Calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant based on the mobility pattern of each target participant, wherein the self-coverage rate represents the amount of the mission area covered by the vehicle trajectory of the target participant, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate; Step 3: for each target participant, compare the vehicle trajectories of any two target participants to obtain the correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation; Step 4: combining the target participants according to the self-coverage, the uncertainty of the self-coverage, and the uncertainty of the coverage between the target participants to obtain a combination result, and calculating the overall coverage of the combination result and the uncertainty of the overall coverage; Step 5: calculating a range of the uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and setting a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of the uncertainty of the overall coverage rate; Step 6: Solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factor to obtain a combination weight matrix, and determine the combination plan of the target participants based on the combination weight matrix; Step 7: Perform task allocation according to the combination plan of the target participants to obtain a task allocation result.

2. The method for allocating group intelligence perception tasks according to claim 1, characterized in that: In step 2, the self-coverage of each target participant is: in, represents the mean coverage rate generated by the i-th target participant completing the t-th round of tasks, represents the set of areas that the vehicle trajectory of the i-th target participant passes through when completing the t-th round of tasks, Represents a region set The number of target regions in l m Represents a region set The mth target area in v m represents the coverage of the mth target area; According to the standard deviation of the self-coverage rate of each target participant, the uncertainty of the self-coverage rate of each target participant is: in, represents the uncertainty of the self-coverage rate of the i-th target participant; N i V represents the cumulative number of tasks completed by the i-th target participant; i represents the mean coverage resulting from the target participant completing all tasks.

3. The method for allocating group intelligence perception tasks according to claim 2, characterized in that: In step 3, the uncertainty of the coverage between the two target participants is calculated by citing the global sequence alignment algorithm as: in, represents the uncertainty of the coverage between the i1th target participant and the i2th target participant; represents the optimal alignment path optimized by the i1th target participant; represents the optimal alignment path optimized by the i2th target participant; Represents the optimal alignment path length; express and The number of identical nodes in .

4. The method for allocating group intelligence perception tasks according to claim 3, characterized in that: In step 4, multiple target participants are combined to obtain a combined result, and the coverage rate of each target participant in the combined result is weighted to obtain the overall coverage rate V p for: Where I represents the number of participants in the combined target; w i represents the weight of the i-th target participant in the combination; According to the correlation of the coverage rates between the two target participants, the uncertainty of the overall coverage rate is obtained by performing a weighted combination and addition of the coverage rates of the target participants: in, represents the uncertainty of the overall coverage.

5. The method for allocating group intelligence perception tasks according to claim 4, characterized in that: In step 5, the regulatory factor The expression is: in, The trade-off between uncertainty and coverage set for the crowd sensing platform is in the range of (0,1). The larger it is, the more the crowdsensing platform tends to increase the uncertainty of the overall task coverage; represents the maximum value of the uncertainty of the overall coverage after combining the target participants; represents the minimum uncertainty of the overall coverage after combining the target participants; f(·) represents the optimal case when V p about The functional relationship of a=V T A -1 V,b=V T A -1 1 I , V represents the matrix composed of the mean coverage of all target participants completing the task, A represents the covariance matrix of coverage between target participants, 1 I represents a 1×I matrix with all 1s, V T represents the matrix transpose of V, A -1 represents the inverse of matrix A, Represents matrix 1 I Transpose, λ i is the eigenvalue of the covariance matrix of the uncertainty of the i-th target participant, represents the minimum uncertainty of the coverage of all target participants themselves, It represents the maximum value of the uncertainty of the coverage of all target participants themselves.

6. The method for allocating group intelligence perception tasks according to claim 5, characterized in that: In step 6, according to the regulatory factor Solve the overall coverage and the uncertainty of the overall coverage to obtain the combined weight matrix for: Among them, A -1 Indicates the inverse of matrix A, V p represents the overall coverage, represents the uncertainty of the overall coverage, and V represents the matrix composed of the mean coverage of all target participants completing the task.

7. The method for allocating group intelligence perception tasks according to claim 6, characterized in that: The combination scheme of the target participants is the combination weight matrix Center front The target participants with large weights are Indicates the number of target participants to be selected.

8. A group intelligence perception task allocation device, characterized in that: include: An acquisition module is configured to acquire historical trajectory data of multiple target participants in the crowdsensing platform and determine the movement pattern of each target participant based on the historical trajectory data, wherein the movement pattern includes vehicle speed and regional distribution of vehicle trajectory; a calculation module, configured to calculate the self-coverage rate and the uncertainty of the self-coverage rate of each target participant according to the movement pattern of each target participant, wherein the self-coverage rate represents the amount of the task area covered by the vehicle trajectory of the target participant, and the uncertainty of the self-coverage rate represents the fluctuation of the self-coverage rate; a comparison module, configured to compare the vehicle trajectories of any two target participants for each target participant, obtain a correlation between the two vehicle trajectories, and calculate the uncertainty of the coverage between the two target participants based on the correlation; a combining module, configured to combine a plurality of target participants according to their own coverage, the uncertainty of their own coverage, and the uncertainty of coverage between the target participants, to obtain a combined result, and to calculate the overall coverage of the combined result and the uncertainty of the overall coverage; a control factor setting module, configured to calculate a range of uncertainty of the overall coverage rate according to the overall coverage rate and the uncertainty of the overall coverage rate, and to set a control factor for controlling the overall coverage rate and the uncertainty of the overall coverage rate based on the range of uncertainty of the overall coverage rate; a solution module, configured to solve the overall coverage rate and the uncertainty of the overall coverage rate according to the control factor to obtain a combination weight matrix, and determine a combination scheme of the target participants based on the combination weight matrix; The task allocation module is used to allocate tasks according to the combination plan of the target participants and obtain task allocation results.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for allocating crowd intelligence tasks according to any one of claims 1 to 7 is implemented.

10. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for allocating crowd intelligence tasks according to any one of claims 1 to 7 is implemented.

Images